Aidimag
Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.
Connector by AiDimag · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/aidimag-aidimag
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.
- Tools
- 13 read · 6 write · 1 delete · 1 not yet classified
- Secrets
- 1 (API keys, tokens or passwords)
- Install scripts
- None found
- Runs as
- Node.js package
Tools by what they do 21
Read from the source code; the running server may list different tools.
Read 13 · Look things up without changing anything.
aidimag_helpchat_harvestcontext_noteknowledge_pendingmemory_check_changememory_critiquememory_get_for_filesmemory_searchmemory_statusmemory_verifyproposals_pendingscratchpad_read
Show 1 more tools
ticket_get
Write 6 · Create, change, send or run things.
commits_mineknowledge_ingest_submitmemory_pre_editmemory_refutememory_writescratchpad_write
Delete 1 · Delete, drop, revoke or wipe things.
scratchpad_clear
Not yet classified 1 · We could not tell from the name and description.
memory_propose
Secrets and settings it asks for
Secrets: values you paste in that let it act as you.
OPENAI_API_KEY
Other settings (environment variables or headers).
AIDIMAG_LLMAIDIMAG_REPO
Network hosts it talks to 33
accounts.google.com· found in codeacme.atlassian.net· found in codeacme.youtrack.cloud· found in codeaidimag.com· found in codeapi.app.shortcut.com· found in codeapi.clickup.com· found in codeapi.github.com· found in codeapi.iconify.design· found in codeapi.linear.app· found in codeapi.notion.com· found in codeapi.openai.com· found in codeapi.trello.com· found in codeapp.asana.com· found in codeapp.clickup.com· found in codeapp.shortcut.com· found in codeasana.com· found in codecdn.jsdelivr.net· found in codecloud.aidimag.com· found in codedev.azure.com· found in codefonts.googleapis.com· found in codefonts.gstatic.com· found in codegithub.com· found in codegitlab.com· found in codeglama.ai· found in codegoogletagmanager.com· found in codeid.atlassian.com· found in codejetbrains.com· found in codelinear.app· found in codenotion.so· found in codeollama.com· found in code
Show 3 more hosts
pivotaltracker.com· found in codetickets.internal.acme.com· found in codetrello.com· found in code
Files it touches
/dev/null/opt/homebrew/bin/ollama- Your home directory (~)
- Any path the agent passes to its tools
Tools (21)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
aidimag_helpShow what aidimag offers: available tools, prompts (slash commands), resources, and the companion `dim` CLI commands. Call this when the user asks what aidimag can do, how to use it, or types 'aidimag help' — then relay the overview to them.
chat_harvestHarvest the CURRENT chat session on the fly: pass the messages the USER typed this session (verbatim) and durable facts are extracted and queued for human review — the live, tool-agnostic equivalent of `dim harvest`. Works from ANY IDE/agent (Copilot, Cursor, Codex, Claude, Devin, …), including cloud tools with no local transcripts. Call at session end, or after a long exchange rich in project knowledge. Secrets are redacted server-side before any LLM sees the text. For single facts stated in passing, prefer context_note instead.
commits_mineMine git commit history for memory-worthy candidates (same as `dim mine`). Queues proposals for `dim review` — never writes active memory directly. Use after meaningful commits, or with full=true to rescan all history.
context_noteCapture a durable fact the USER just stated in chat. Call this IMMEDIATELY when the user shares codebase knowledge — don't wait for session end. ALWAYS trigger on: 'we use X because Y' (DECISION), 'never do X' (GUARDRAIL), 'we always X' (CONVENTION), 'we tried X, it failed' (FAILED_APPROACH), 'the architecture is...' (ARCHITECTURE). Skip task-specific requests like 'fix this bug'. User-stated facts are queued for review with high trust (HUMAN_ATTESTED evidence).
knowledge_ingest_submitSubmit the FALSIFIABLE claims you extracted from a pending knowledge doc (see the knowledge_ingest prompt). Queues them as proposals (source knowledge:<doc>), writes the durable summary, backs up the original, and clears the inbox copy. Claims become PINNED memory only after `dim review` (unless the repo opted out).
knowledge_pendingList documents waiting in the knowledge inbox to be summarized into pinned-on-approve memory proposals. Use with the knowledge_ingest prompt to process them in-session.
memory_check_changePre-edit safety check: given a diff or a short description of a change you're about to make, return any FAILED_APPROACH, GUARDRAIL, INVARIANT, or CONVENTION memories that match. Call this BEFORE editing code when the task touches an area with known historical failures or explicit rules. Returns a decision: proceed, ask_first, or stop.
memory_critiqueReview what you just did (or plan to do) against the project's VERIFIED memory and guardrails — a 'second critic' grounded in real, falsifiable beliefs rather than another model's opinion. Call BEFORE committing or proposing memories. Resolve guardrail violations and contradictions first.
memory_get_for_filesGet all memories relevant to specific files before editing them — conventions, gotchas, and invariants that apply to those paths.
memory_pre_editPre-edit guardrail check for a specific file and code snippet. Given a file path and the code you're about to write, check whether it violates any NEVER guardrails or triggers FAILED_APPROACH warnings. Returns a clear STOP/PROCEED decision. Call this before writing to files in protected areas.
memory_proposePropose a memory for the human review queue. Use at SESSION END for learnings that should persist but warrant review before becoming active memory. Prefer this over memory_write for inferred/uncertain knowledge.
memory_refuteMark a memory as REFUTED when you discover it no longer holds. Optionally provide the id of a new memory that supersedes it. Refuted memories are kept as negative knowledge.
memory_searchSearch the repo's verified memory for decisions, conventions, gotchas, failed approaches, and invariants. Use BEFORE exploring the codebase — past sessions may already know the answer.
memory_statusGet a summary of the repo's memory store: counts by verification status and kind.
memory_verifyRe-run cheap evidence checks (STATIC_CHECK, COMMIT_REF) and update memory statuses. Use before relying on VERIFIED memories if the repo may have changed, or to verify specific memories by id.
Show 6 more tools
memory_writePersist a new memory about this codebase. Write the claim as a FALSIFIABLE statement (something that could be checked against the code). Attach evidence whenever possible. For kind=GUARDRAIL, set guardrail_level (never|always|ask-first).
proposals_pendingList memory proposals awaiting human review.
scratchpad_clearClear scratchpad working notes (one session key, or everything). Use when a task completes and its intermediate state is no longer needed.
scratchpad_readRead short-term working notes from the current session's scratchpad (newest first). Use at session start or when resuming a task to recover in-flight state. Expired notes are purged automatically.
scratchpad_writeJot a SHORT-TERM working note for the current session: intermediate findings, plans, hypotheses, task state. Auto-expires (default 24h) and is never synced. NOT durable memory — use memory_write/memory_propose for knowledge that should persist across sessions.
ticket_getFetch the ticket behind the current work (title, description, type, status) from the connected ticketing app. Use at session end: the ticket carries the WHY that commits lack. Omit the id to auto-detect it from the current branch name.
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit
- Oct 8, 2026 (21 days ago)
- Last release
- Oct 8, 2026 (21 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.AiDimag/aidimag- Version
- 1.0.22
- Auth
- API key
- Packages
- npm aidimag
- License
- MIT
- Repository
- github.com/AiDimag/aidimag
- Website
- aidimag.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 25, 2026
Cite this page
Aidimag MCP server. Agent Mart. https://agentmart.dev/connectors/aidimag-aidimag (last updated 2026-10-25)